Serve vision models with their projector and original weights on vLLM; group the mirror by version

model serve takes --projector, fetched beside the weights and loaded by
llama.cpp with --mmproj, and --format safetensors with --gpu-class and --tp,
which fetches the weights with their config and tokenizer and runs them on
vLLM. The console offers both, F switching between GGUF and original
weights. The mirror view is one row per version with its files on Enter.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-04 00:42:59 +02:00
1 parent 7aefb236d6
commit a16097cfe8
12 files changed
+509 -81

No files matched your search

+9 -3
View File
@@ -292,7 +292,7 @@ func (m consoleModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
case consoleMirrorMsg:
m.mirror = msg
case consoleHFMsg:
if msg.query == m.hf.query && msg.sort == m.hf.sort {
if msg.query == m.hf.query && msg.sort == m.hf.sort && msg.st == m.hf.safetensors {
m.hf.models, m.hf.err = msg.models, msg.err
if m.hf.models == nil && msg.err == nil {
m.hf.models = []hf.Model{}
@@ -447,7 +447,7 @@ func (m consoleModel) key(k tea.KeyMsg) (tea.Model, tea.Cmd) {
case cQuotas:
m.menuD = m.quotaMenu(m.quotas[m.row])
case cMirror:
m.menuD = m.mirrorMenu(m.mirror.res.Models[m.row])
m.menuD = m.mirrorMenu(m.mirrorGroups()[m.row])
case cServe:
return m, m.fetchRepo(m.hf.models[m.row].ID)
case cAccounts:
@@ -464,6 +464,12 @@ func (m consoleModel) key(k tea.KeyMsg) (tea.Model, tea.Cmd) {
if m.menu == cServe {
m.hfSearchDialog()
}
case "f":
if m.menu == cServe {
m.hf.safetensors = !m.hf.safetensors
m.hf.models, m.hf.err, m.row = nil, nil, 0
return m, m.fetchHF()
}
case "s":
if m.menu == cServe {
m.hf.sort = (m.hf.sort + 1) % len(hfSorts)
@@ -824,7 +830,7 @@ func (m consoleModel) rowCount() int {
case cQuotas:
return len(m.quotas)
case cMirror:
return len(m.mirror.res.Models)
return len(m.mirrorGroups())
case cServe:
return len(m.hf.models)
case cAccounts: